Generating high-resolution land cover maps using relatively lower-resolution remote sensing images is of great importance for subtle analysis. However, the domain gap between real lower-resolution and synthetic images has not been permanently resolved. Furthermore, super-resolution information is not fully exploited in semantic segmentation models. By solving the aforementioned issues, a deeply fused super resolution guided semantic segmentation network using 30 m Landsat images is proposed. A large-scale dataset comprising 10 m Sentinel-2, 30 m Landsat-8 images, and 10 m European Space Agency (ESA) Land Cover Product is introduced, facilitating model training and evaluation across diverse real-world scenarios. The proposed Deeply Fused Super Resolution Guided Semantic Segmentation Network (DFSRSSN) combines a Super Resolution Module (SRResNet) and a Semantic Segmentation Module (CRFFNet). SRResNet enhances spatial resolution, while CRFFNet leverages super-resolution information for finer-grained land cover classification. Experimental results demonstrate the superior performance of the proposed method in five different testing datasets, achieving 68.17–83.29% and 39.55–75.92% for overall accuracy and kappa, respectively. When compared to ResUnet with up-sampling block, increases of 2.16–34.27% and 8.32–43.97% were observed for overall accuracy and kappa, respectively. Moreover, we proposed a relative drop rate of accuracy metrics to evaluate the transferability. The model exhibits improved spatial transferability, demonstrating its effectiveness in generating accurate land cover maps for different cities. Multi-temporal analysis reveals the potential of the proposed method for studying land cover and land use changes over time. In addition, a comparison of the state-of-the-art full semantic segmentation models indicates that spatial details are fully exploited and presented in semantic segmentation results by the proposed method.

China’s vast rural landscape exhibits pronounced regional disparities in both foundational resources and development potential. In the context of nationwide rural revitalization efforts, the emergent divergence in village development pathways underscores a pressing need for context-specific, classified interventions. To furnish a scientifically grounded typology of villages and inform differentiated development planning, this investigation focuses on Hubei Province as an illustrative case. Synthesizing survey data from 32,457 villages, we developed a multidimensional evaluation framework encompassing four pivotal domains: economic vitality, social service provision, ecological integrity, and cultural value. Leveraging the Self-Organizing Feature Map (SOFM) neural network—an unsupervised machine learning algorithm—we performed a cluster analysis on multi-source, heterogeneous datasets. This technique enabled the objective delineation of spatial typological patterns among Hubei’s villages, elucidated their underlying classification architecture shaped by multifaceted drivers, and demonstrated the methodological robustness and applicability of this approach for large-scale village categorization. Grounded in the derived typologies and informed by strategic directives from higher-tier planning instruments, we conducted a nuanced examination of the distinctive attributes characterizing each village type. The findings provide scientific evidence and decision-making support for village classification and rural revitalization planning in Hubei Province, with valuable implications for other regions with similar development foundations in China.

Understanding how long-term local climate zone (LCZ) dynamics interact with rapid urbanization and land surface temperature (LST) changes is essential for sustainable planning in megaregion-scale urban clusters. In this paper, we propose a multi-feature local sample transfer method to obtain LCZ maps from 2000 to 2020 in the Guangdong–Hong Kong–Macao Greater Bay Area (GBA) and then analyze spatiotemporal changes in LCZs and their impacts on surface thermal environments. Results show the following: (1) The proposed multi-feature local sample transfer approach significantly improves the efficiency of long-term LCZ mapping by greatly reducing the effort required for sample acquisition. (2) The built types (LCZ1–10) increased by 1.34% overall, with large low-rise (LCZ8) showing the greatest expansion (4.72%). The compact low-rise (LCZ3) was the only built type to decline, decreasing by 2.02%. (3) Urbanization has produced a contiguous warming core that expands outward from the central metropolitan zones, thereby promoting the UHI coalescence. (4) Dense trees (LCZA) and large low-rise (LCZ8) exerted the strongest influence on LST. Large low-rise (LCZ8) consistently exhibited the highest warming contribution in Foshan, Zhongshan, and Dongguan. In coastal cities including Shenzhen, Hong Kong, and Macao, the largest LST increases occurred when water (LCZG) areas were converted to bare rock or paved (LCZE) or cs (LCZ1–10). Overall, the results highlight the strong coupling between urbanization and surface heating, providing critical insights for urban climate adaptation and integrated land-use planning in rapidly urbanizing megaregions.

This study investigates the spatial association between metro network topological centrality and the distribution of commercial establishments in Wuhan, China, with attention to its implications for sustainable urban development. Metro station data and commercial point-of-interest (POI) data were integrated with space syntax and GIS-based spatial analysis to examine commercial spatial patterns at both the citywide and station levels. Kernel density estimation was used to identify commercial agglomerations, while station-level Spearman correlation analysis, bootstrap comparison, Gini coefficient analysis, and Local Moran’s I were employed to evaluate the spatial association between metro network topological centrality and different commercial sectors. The results show that: (1) Wuhan exhibits a “primary core–multiple nodes” commercial spatial structure, and the current distribution of commercial establishments differs among planned city-level commercial centers despite their comparable planning hierarchy. (2) A significant positive spatial association exists between metro network topological centrality and commercial establishment distribution at the station level. However, substantial spatial heterogeneity is observed across the network. For example, Optics Valley Square and Zhuyehai contain relatively dense commercial establishments despite comparatively low topological centrality, whereas Wuhan Business District Station exhibits relatively high topological centrality but limited surrounding commercial development. (3) All seven commercial sectors show significant positive spatial associations with metro network topological centrality, although finance exhibits the strongest association. The remaining sectors display broadly comparable correlation strengths but differ considerably in their spatial concentration patterns. These findings enhance understanding of the spatial organization of commercial activities in relation to metro network topology and provide empirical evidence to support commercial planning, transit-oriented urban development, and more sustainable patterns of urban commercial development.